skills.rest
wjgoarxiv
wjgoarxivCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

autoconference

Orchestrate multi-agent research into structured conference rounds with peer review.

5|Updated Mar 18, 2026
Search Tags:#automation#multi-agent#synthesis#event logging#adversarial review#research conference#convergence detection
One-click install
npx skills add https://github.com/wjgoarxiv/autoconference-skill --skill autoconference
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: autoconference
Source: https://github.com/wjgoarxiv/autoconference-skill/tree/main/skills/autoconference
Command: npx skills add https://github.com/wjgoarxiv/autoconference-skill --skill autoconference

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

It coordinates multiple autonomous researchers into structured, round-based collaboration and adversarial peer review so you can reliably synthesize better results than a single agent run.

Core Features & Use Cases

  • Parallel autoresearch with conference rounds: Spawns N researcher agents that iteratively research, evaluate, and log results across independent research, poster session, peer review, and knowledge transfer phases.
  • Adversarial validation and synthesis: Uses a reviewer step to challenge claims, validate or overturn findings, and then transfers only validated knowledge into shared state.
  • Convergence and crash recovery guardrails: Detects convergence or budget/stall stop conditions and supports recovery via an event log for interrupted conferences.

Quick Start

Create a conference.md that defines your Goal, Mode, Success Metric or Success Criteria, and search space, then ask the autoconference skill to run the conference using that file for your desired researcher count and strategy partitioning.

Frequently Asked Questions about autoconference

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I coordinate multiple autonomous agents for parallel research and synthesis?▼

Multi-agent autonomous research coordinates multiple agents into structured conference rounds, using parallel partitioned exploration and adversarial peer review to synthesize validated outcomes across researchers.

What is adversarial peer review in autonomous multi-agent research?▼

Adversarial peer review is a validation phase where a reviewer agent challenges research claims to validate or overturn findings, transferring only validated knowledge into the shared state for final synthesis.

How do I run a multi-agent research conference using a markdown configuration?▼

Create a conference.md file defining your goal, mode, success criteria, and search space, then execute the conference to spawn parallel researchers with chair, reviewer, and synthesizer phases.

Can I recover an interrupted multi-agent research run if it crashes or stalls?▼

Interrupted multi-agent research runs support crash recovery via event logging, detecting budget limits or stall conditions to terminate and resume structured conference rounds.

When should I use a multi-agent conference approach instead of a single agent for large search spaces?▼

Use multi-agent conferences for large search spaces requiring partitioned exploration, iterative knowledge transfer, and adversarial validation to reliably synthesize better results than a single agent.

Does multi-agent research synthesis require specific termination criteria?▼

Multi-agent research synthesis requires convergence detection or budget-based termination criteria, stopping conference rounds automatically when agents reach stable findings or exhaust allocated resources.

Related Skills

Explore More Education & Research Skills→
jeremydhoover-blipjeremydhoover-blip
7

designing-agent-workflows

Design multi-step agent workflows with decision trees and state machines.

Community
Advanced
wjgoarxivwjgoarxiv
5

autoconference:resume

Resume interrupted autoconference research from a persisted event log.

Community
Advanced
eaasxteaasxt

execute

Coordinate parallel bead execution across agent workers with phase calibration.

Community
Advanced
wjgoarxivwjgoarxiv
5

autoconference-skill

Orchestrate parallel autoresearchers with adversarial peer review and fused synthesis.

Community
Advanced